Card: the branch windows-model-zoo

0c1be83 verified 3 days ago

6.58 kB

---
license: apache-2.0
base_model: litert-community/RTMPose-s-LiteRT
base_model_relation: quantized
library_name: openvino
pipeline_tag: keypoint-detection
tags:
- openvino
- onnx
- intel-npu
---
# RTMPose-s-OpenVINO

RTMPose-s for Intel NPUs, GPUs and CPUs: rtmpose_s_fp16 from [litert-community/RTMPose-s-LiteRT](https://huggingface.co/litert-community/RTMPose-s-LiteRT/tree/9cc07fa96de442bcc568f2cbb442e94fbfe4dac2) as ONNX (tf2onnx 1.17.0, opset 17), OpenVINO IR with fp32 weights, and a precompiled Intel NPU blob. On the NPU of a Core Ultra 9 386H the blob runs in 0.89 ms per run, numpy input to numpy output.

Scripts, raw records, and the same table for all 52 graphs of LiteRT-Models: https://github.com/john-rocky/windows-zoo

## Files

| file | bytes | sha256 |
|---|---|---|
| `rtmpose_s_fp16.onnx` | 22,197,006 | `6c802b86a0f976f700afc336916a6db593df098b11568803e96d749ef6c8b9f3` |
| `openvino/rtmpose_s_fp16.xml` | 645,133 | `43bc352fc506a2dba6c3c4a6d28c8841d7355862788cf264d61cb2ea0dc2b85e` |
| `openvino/rtmpose_s_fp16.bin` | 21,870,864 | `e67abb3cc341620f5e759c33aafdf66535a6f2e93eb7c2ef99cc8ce5c5a3536c` |
| `npu/rtmpose_s_fp16.blob` | 11,858,056 | `e080cbbab273a719570224f9795a1b88873b0ff8246f051a7b0316d5b78239ed` |

The NPU blob was compiled with OpenVINO 2026.4.1, Intel NPU driver 32.0.100.4841 (OpenVINO reports NPU_DRIVER_VERSION 1004841, NPU_COMPILER_VERSION 524292). If `import_model` refuses a blob on another driver or OpenVINO version, compile the IR instead (the commented line in the snippet).

## How it was measured

MSI Stealth 16 AI+ (Core Ultra 9 386H, RTX 5080 Laptop GPU at a 95 W power limit, Windows 11 build 26200.9711, on AC power), 2026-11-06 to 2026-11-07. On the laptop, each row is one process: load, one run, 5 warmup runs, then the median of 30 timed runs (2 warmup + 10 timed runs when the first run takes more than 3 s), numpy input to numpy output, every runtime at its default settings, one process at a time, each started after the CPU, the RTX and the Intel GPU had gone idle (the thresholds are in METHOD.md of the GitHub repo). Output check: each output against the CPU output in fp32 on the same input (ONNX Runtime's CPU EP); PASS = cosine ≥ 0.99, no NaN or Inf, and top-1 agreement ≥ 0.99 for class scores. The Snapdragon rows are Qualcomm AI Hub profile jobs of the same ONNX files (their own timer).

## Speed and output check

| processor | runtime | file | ms | load s | output check |
|---|---|---|---|---|---|
| Intel AI Boost NPU | OpenVINO 2026.4.1 | `npu/` blob (`import_model`) | 0.89 | 0.01 | FAIL: output_0_output: cos 0.9367 < 0.99; output_0_output: argmax agreement 15/17; output_1_output: cos 0.9374 < 0.99; output_1_output: argmax agreement 10/17 |
| Intel AI Boost NPU | ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1 | `.onnx`, compiled when the session loads | 1.17 | 0.95 | FAIL: output_0_output: cos 0.9367 < 0.99; output_0_output: argmax agreement 15/17; output_1_output: cos 0.9374 < 0.99; output_1_output: argmax agreement 10/17 |
| Intel Graphics (iGPU) | ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1 | `.onnx` | 0.66 | 0.45 | PASS (cos ≥ 0.9999) |
| RTX 5080 Laptop (95 W limit) | ONNX Runtime 1.31.1, CUDA EP | fp16 copy of the `.onnx` (not in this repo) | 2.72 | 1.26 | FAIL: output_0_output: argmax agreement 16/17; output_1_output: argmax agreement 15/17 |
| RTX 5080 Laptop (95 W limit) | ONNX Runtime 1.31.1, CUDA EP | `.onnx` | 2.94 | 1.16 | FAIL: output_1_output: argmax agreement 16/17 |
| Core Ultra 9 386H CPU | ONNX Runtime 1.31.1, CPU EP | `.onnx` | 3.23 | 0.07 | reference |
| Snapdragon X2 Elite NPU | Qualcomm AI Hub, precompiled QNN ONNX | `.onnx` compiled by AI Hub | 0.44 | 0.44 | not compared (AI Hub profile job, 2026-10-30) |
| Snapdragon X2 Elite NPU | Qualcomm AI Hub, ONNX Runtime QNN EP | `.onnx`, compiled when it loads | 0.42 | 0.79 | not compared (AI Hub profile job, 2026-10-30) |
| Galaxy S26 NPU | Qualcomm AI Hub, precompiled QNN ONNX | `.onnx` compiled by AI Hub | 0.36 | 0.15 | not compared (AI Hub profile job, 2026-10-30) |

The ONNX file against the source `.tflite` (LiteRT interpreter on the CPU, the same input): PASS, cosine ≥ 0.9999 for every output.

## Run it on the Intel NPU

Download this repo, then run the snippets from its folder:

```sh
pip install huggingface_hub
hf download mlboydaisuke/RTMPose-s-OpenVINO --local-dir RTMPose-s-OpenVINO
cd RTMPose-s-OpenVINO
```

OpenVINO (`pip install openvino==2026.4.1`):

```python
import numpy as np
import openvino as ov
core = ov.Core()
if "NPU" not in core.available_devices:
    raise SystemExit(f"no Intel NPU visible to OpenVINO: {core.available_devices}")
with open("npu/rtmpose_s_fp16.blob", "rb") as f:
    compiled = core.import_model(f.read(), "NPU")  # precompiled: no compile at load
# or compile the IR on this machine: compiled = core.compile_model("openvino/rtmpose_s_fp16.xml", "NPU")
# replace the zeros with your preprocessed input (float32, the shapes printed by compiled.inputs)
feeds = {i.get_any_name(): np.zeros(list(i.shape), np.float32) for i in compiled.inputs}
outputs = compiled(feeds)
print({o.get_any_name(): outputs[o].shape for o in compiled.outputs})
```

ONNX Runtime with the OpenVINO EP (`pip install onnxruntime==1.31.1 onnxruntime-ep-openvino==1.8.1`):

```python
import numpy as np
import onnxruntime as ort
import onnxruntime_ep_openvino as ov_ep
ort.register_execution_provider_library(ov_ep.get_ep_name(), ov_ep.get_library_path())
npu = [d for d in ort.get_ep_devices()
       if d.ep_name == ov_ep.get_ep_name() and d.ep_metadata.get("ov_device") == "NPU"]
if not npu:
    raise SystemExit("no Intel NPU visible to the OpenVINO EP")
so = ort.SessionOptions()
so.add_provider_for_devices(npu, {})
sess = ort.InferenceSession("rtmpose_s_fp16.onnx", sess_options=so)  # compiles for the NPU here
# replace the zeros with your preprocessed input (float32)
feeds = {i.name: np.zeros(i.shape, np.float32) for i in sess.get_inputs()}
outputs = sess.run(None, feeds)
print([o.shape for o in outputs])
```

## Branch `windows-model-zoo`

The branch [`windows-model-zoo`](https://huggingface.co/mlboydaisuke/RTMPose-s-OpenVINO/tree/windows-model-zoo) adds the file that [windows-model-zoo](https://github.com/john-rocky/windows-model-zoo) runs. `fp16/`: the fp16 copy that the RTX fp16 row above ran. To use the model, take main's files.

## Licence

Apache-2.0, the licence of [litert-community/RTMPose-s-LiteRT](https://huggingface.co/litert-community/RTMPose-s-LiteRT). The source card names the upstream model as `open-mmlab/mmpose` (not a Hugging Face repo).

	---
	license: apache-2.0
	base_model: litert-community/RTMPose-s-LiteRT
	base_model_relation: quantized
	library_name: openvino
	pipeline_tag: keypoint-detection
	tags:
	- openvino
	- onnx
	- intel-npu
	---

	# RTMPose-s-OpenVINO

	RTMPose-s for Intel NPUs, GPUs and CPUs: rtmpose_s_fp16 from [litert-community/RTMPose-s-LiteRT](https://huggingface.co/litert-community/RTMPose-s-LiteRT/tree/9cc07fa96de442bcc568f2cbb442e94fbfe4dac2) as ONNX (tf2onnx 1.17.0, opset 17), OpenVINO IR with fp32 weights, and a precompiled Intel NPU blob. On the NPU of a Core Ultra 9 386H the blob runs in 0.89 ms per run, numpy input to numpy output.

	Scripts, raw records, and the same table for all 52 graphs of LiteRT-Models: https://github.com/john-rocky/windows-zoo

	## Files

	\| file \| bytes \| sha256 \|
	\|---\|---\|---\|
	\| `rtmpose_s_fp16.onnx` \| 22,197,006 \| `6c802b86a0f976f700afc336916a6db593df098b11568803e96d749ef6c8b9f3` \|
	\| `openvino/rtmpose_s_fp16.xml` \| 645,133 \| `43bc352fc506a2dba6c3c4a6d28c8841d7355862788cf264d61cb2ea0dc2b85e` \|
	\| `openvino/rtmpose_s_fp16.bin` \| 21,870,864 \| `e67abb3cc341620f5e759c33aafdf66535a6f2e93eb7c2ef99cc8ce5c5a3536c` \|
	\| `npu/rtmpose_s_fp16.blob` \| 11,858,056 \| `e080cbbab273a719570224f9795a1b88873b0ff8246f051a7b0316d5b78239ed` \|

	The NPU blob was compiled with OpenVINO 2026.4.1, Intel NPU driver 32.0.100.4841 (OpenVINO reports NPU_DRIVER_VERSION 1004841, NPU_COMPILER_VERSION 524292). If `import_model` refuses a blob on another driver or OpenVINO version, compile the IR instead (the commented line in the snippet).

	## How it was measured

	MSI Stealth 16 AI+ (Core Ultra 9 386H, RTX 5080 Laptop GPU at a 95 W power limit, Windows 11 build 26200.9711, on AC power), 2026-11-06 to 2026-11-07. On the laptop, each row is one process: load, one run, 5 warmup runs, then the median of 30 timed runs (2 warmup + 10 timed runs when the first run takes more than 3 s), numpy input to numpy output, every runtime at its default settings, one process at a time, each started after the CPU, the RTX and the Intel GPU had gone idle (the thresholds are in METHOD.md of the GitHub repo). Output check: each output against the CPU output in fp32 on the same input (ONNX Runtime's CPU EP); PASS = cosine ≥ 0.99, no NaN or Inf, and top-1 agreement ≥ 0.99 for class scores. The Snapdragon rows are Qualcomm AI Hub profile jobs of the same ONNX files (their own timer).

	## Speed and output check

	\| processor \| runtime \| file \| ms \| load s \| output check \|
	\|---\|---\|---\|---\|---\|---\|
	\| Intel AI Boost NPU \| OpenVINO 2026.4.1 \| `npu/` blob (`import_model`) \| 0.89 \| 0.01 \| FAIL: output_0_output: cos 0.9367 < 0.99; output_0_output: argmax agreement 15/17; output_1_output: cos 0.9374 < 0.99; output_1_output: argmax agreement 10/17 \|
	\| Intel AI Boost NPU \| ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1 \| `.onnx`, compiled when the session loads \| 1.17 \| 0.95 \| FAIL: output_0_output: cos 0.9367 < 0.99; output_0_output: argmax agreement 15/17; output_1_output: cos 0.9374 < 0.99; output_1_output: argmax agreement 10/17 \|
	\| Intel Graphics (iGPU) \| ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1 \| `.onnx` \| 0.66 \| 0.45 \| PASS (cos ≥ 0.9999) \|
	\| RTX 5080 Laptop (95 W limit) \| ONNX Runtime 1.31.1, CUDA EP \| fp16 copy of the `.onnx` (not in this repo) \| 2.72 \| 1.26 \| FAIL: output_0_output: argmax agreement 16/17; output_1_output: argmax agreement 15/17 \|
	\| RTX 5080 Laptop (95 W limit) \| ONNX Runtime 1.31.1, CUDA EP \| `.onnx` \| 2.94 \| 1.16 \| FAIL: output_1_output: argmax agreement 16/17 \|
	\| Core Ultra 9 386H CPU \| ONNX Runtime 1.31.1, CPU EP \| `.onnx` \| 3.23 \| 0.07 \| reference \|
	\| Snapdragon X2 Elite NPU \| Qualcomm AI Hub, precompiled QNN ONNX \| `.onnx` compiled by AI Hub \| 0.44 \| 0.44 \| not compared (AI Hub profile job, 2026-10-30) \|
	\| Snapdragon X2 Elite NPU \| Qualcomm AI Hub, ONNX Runtime QNN EP \| `.onnx`, compiled when it loads \| 0.42 \| 0.79 \| not compared (AI Hub profile job, 2026-10-30) \|
	\| Galaxy S26 NPU \| Qualcomm AI Hub, precompiled QNN ONNX \| `.onnx` compiled by AI Hub \| 0.36 \| 0.15 \| not compared (AI Hub profile job, 2026-10-30) \|

	The ONNX file against the source `.tflite` (LiteRT interpreter on the CPU, the same input): PASS, cosine ≥ 0.9999 for every output.

	## Run it on the Intel NPU

	Download this repo, then run the snippets from its folder:

	```sh
	pip install huggingface_hub
	hf download mlboydaisuke/RTMPose-s-OpenVINO --local-dir RTMPose-s-OpenVINO
	cd RTMPose-s-OpenVINO
	```

	OpenVINO (`pip install openvino==2026.4.1`):

	```python
	import numpy as np
	import openvino as ov

	core = ov.Core()
	if "NPU" not in core.available_devices:
	raise SystemExit(f"no Intel NPU visible to OpenVINO: {core.available_devices}")
	with open("npu/rtmpose_s_fp16.blob", "rb") as f:
	compiled = core.import_model(f.read(), "NPU") # precompiled: no compile at load
	# or compile the IR on this machine: compiled = core.compile_model("openvino/rtmpose_s_fp16.xml", "NPU")
	# replace the zeros with your preprocessed input (float32, the shapes printed by compiled.inputs)
	feeds = {i.get_any_name(): np.zeros(list(i.shape), np.float32) for i in compiled.inputs}
	outputs = compiled(feeds)
	print({o.get_any_name(): outputs[o].shape for o in compiled.outputs})
	```

	ONNX Runtime with the OpenVINO EP (`pip install onnxruntime==1.31.1 onnxruntime-ep-openvino==1.8.1`):

	```python
	import numpy as np
	import onnxruntime as ort
	import onnxruntime_ep_openvino as ov_ep

	ort.register_execution_provider_library(ov_ep.get_ep_name(), ov_ep.get_library_path())
	npu = [d for d in ort.get_ep_devices()
	if d.ep_name == ov_ep.get_ep_name() and d.ep_metadata.get("ov_device") == "NPU"]
	if not npu:
	raise SystemExit("no Intel NPU visible to the OpenVINO EP")
	so = ort.SessionOptions()
	so.add_provider_for_devices(npu, {})
	sess = ort.InferenceSession("rtmpose_s_fp16.onnx", sess_options=so) # compiles for the NPU here
	# replace the zeros with your preprocessed input (float32)
	feeds = {i.name: np.zeros(i.shape, np.float32) for i in sess.get_inputs()}
	outputs = sess.run(None, feeds)
	print([o.shape for o in outputs])
	```

	## Branch `windows-model-zoo`

	The branch [`windows-model-zoo`](https://huggingface.co/mlboydaisuke/RTMPose-s-OpenVINO/tree/windows-model-zoo) adds the file that [windows-model-zoo](https://github.com/john-rocky/windows-model-zoo) runs. `fp16/`: the fp16 copy that the RTX fp16 row above ran. To use the model, take main's files.

	## Licence

	Apache-2.0, the licence of [litert-community/RTMPose-s-LiteRT](https://huggingface.co/litert-community/RTMPose-s-LiteRT). The source card names the upstream model as `open-mmlab/mmpose` (not a Hugging Face repo).